metadata
license: apache-2.0
base_model: jonas-luehrs/bert-base-cased-MLM-chemistry
tags:
- generated_from_trainer
metrics:
- f1
- precision
- recall
- accuracy
model-index:
- name: bert-base-cased-MLM-chemistry-textCLS-PETROCHEMICAL
results: []
bert-base-cased-MLM-chemistry-textCLS-PETROCHEMICAL
This model is a fine-tuned version of jonas-luehrs/bert-base-cased-MLM-chemistry on an unknown dataset. It achieves the following results on the evaluation set:
- Loss: 0.5312
- F1: 0.7952
- Precision: 0.7860
- Recall: 0.8108
- Accuracy: 0.8108
Model description
More information needed
Intended uses & limitations
More information needed
Training and evaluation data
More information needed
Training procedure
Training hyperparameters
The following hyperparameters were used during training:
- learning_rate: 2e-05
- train_batch_size: 16
- eval_batch_size: 16
- seed: 42
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- num_epochs: 3
Training results
| Training Loss | Epoch | Step | Validation Loss | F1 | Precision | Recall | Accuracy |
|---|---|---|---|---|---|---|---|
| 1.1794 | 1.0 | 125 | 0.6850 | 0.7443 | 0.7550 | 0.7658 | 0.7658 |
| 0.605 | 2.0 | 250 | 0.5785 | 0.7726 | 0.7675 | 0.7883 | 0.7883 |
| 0.4452 | 3.0 | 375 | 0.5312 | 0.7952 | 0.7860 | 0.8108 | 0.8108 |
Framework versions
- Transformers 4.33.2
- Pytorch 2.0.1+cu118
- Datasets 2.14.5
- Tokenizers 0.13.3